-
The University of Hong Kong
- Hong Kong SAR
Stars
Language
Sort by: Recently starred
real time face swap and one-click video deepfake with only a single image
Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).
Agentic components of the Llama Stack APIs
PyTorch implementation of moe, which stands for mixture of experts
Official implementation of "Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks", NeurIPS 2021.
A Topology Layer for Machine Learning : Persistent Homology + Features for PyTorch
[Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers
Repository for research in the field of Responsible NLP at Meta.
Code base for "Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature".
ACL2023 - AlignScore, a metric for factual consistency evaluation.
Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper
Code release for Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML2019)
This is the code of the paper : "fairness guarantee in multi-class classification"
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
Source code for GraB: Quantifying and Reducing Imbalance in Networks
Data and code for Kang et al., NAACL 2018's paper titled "A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications"
Robust machine learning for responsible AI
SemEval2024-task8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detection
Dataset of GPT-2 outputs for research in detection, biases, and more
[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627
Our solution for Recsys Challenge 2017.
Code for the SIGIR20 paper -- Recommendation for New Users and New Items via Randomized Training and Mixture-of-Experts Transformation
Python-based framework for building and evaluating session-based and session-aware recommender systems.
Code for our ACM RecSys 2017 paper "Personalizing Session-based Recommendation with Hierarchical Recurrent Neural Networks"